亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Emergent Properties of Foveated Perceptual Systems

人工智能 计算机科学 人类视觉系统模型 计算机视觉 稳健性(进化) 卷积神经网络 视觉感受 感知 模式识别(心理学) 图像(数学) 生物化学 化学 神经科学 生物 基因
作者
Arturo Deza,Talia Konkle
摘要

We introduce foveated perceptual systems -- a hybrid architecture inspired by human vision, to explore the role of a \textit{texture-based} foveation stage on the nature and robustness of subsequently learned visual representation in machines. Specifically, these two-stage perceptual systems first foveate an image, inducing a texture-like encoding of peripheral information -- mimicking the effects of \textit{visual crowding} -- which is then relayed through a convolutional neural network (CNN) trained to perform scene categorization. We find that these foveated perceptual systems learn a visual representation that is \textit{distinct} from their non-foveated counterpart through experiments that probe: 1) i.i.d and o.o.d generalization; 2) robustness to occlusion; 3) a center image bias; and 4) high spatial frequency sensitivity. In addition, we examined the impact of this foveation transform with respect to two additional models derived with a rate-distortion optimization procedure to compute matched-resource systems: a lower resolution non-foveated system, and a foveated system with adaptive Gaussian blurring. The properties of greater i.i.d generalization, high spatial frequency sensitivity, and robustness to occlusion emerged exclusively in our foveated texture-based models, independent of network architecture and learning dynamics. Altogether, these results demonstrate that foveation -- via peripheral texture-based computations -- yields a distinct and robust representational format of scene information relative to standard machine vision approaches, and also provides symbiotic computational support that texture-based peripheral encoding has important representational consequences for processing in the human visual system.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI2S应助科研通管家采纳,获得10
19秒前
科研通AI2S应助科研通管家采纳,获得10
19秒前
ICSSCI完成签到,获得积分10
24秒前
37秒前
董可以发布了新的文献求助10
41秒前
风华正茂完成签到,获得积分10
1分钟前
1分钟前
1分钟前
jimmy_bytheway完成签到,获得积分0
1分钟前
桃桃发布了新的文献求助10
1分钟前
可爱的函函应助桃桃采纳,获得10
1分钟前
1分钟前
2分钟前
2分钟前
2分钟前
NexusExplorer应助科研通管家采纳,获得10
2分钟前
所所应助爱笑的毛衣采纳,获得10
2分钟前
2分钟前
2分钟前
duan完成签到 ,获得积分10
2分钟前
holder完成签到,获得积分10
3分钟前
3分钟前
沐白发布了新的文献求助10
3分钟前
3分钟前
刘宇童发布了新的文献求助10
3分钟前
大模型应助吕易巧采纳,获得10
3分钟前
迷人问兰完成签到,获得积分10
3分钟前
闪闪映易完成签到 ,获得积分10
3分钟前
3分钟前
吕易巧发布了新的文献求助10
3分钟前
吕易巧完成签到,获得积分10
3分钟前
4分钟前
Liiiiiiiiii发布了新的文献求助10
4分钟前
XuchaoD完成签到,获得积分10
4分钟前
4分钟前
今后应助Liiiiiiiiii采纳,获得10
4分钟前
顾矜应助科研通管家采纳,获得10
4分钟前
Akim应助科研通管家采纳,获得10
4分钟前
4分钟前
4分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3990049
求助须知:如何正确求助?哪些是违规求助? 3532108
关于积分的说明 11256354
捐赠科研通 3270976
什么是DOI,文献DOI怎么找? 1805166
邀请新用户注册赠送积分活动 882270
科研通“疑难数据库(出版商)”最低求助积分说明 809228